Deep exemplar 2d-3d detection by adapting from real to rendered views

Francisco Massa 1, 2, 3 Bryan Russell 4 Mathieu Aubry 1, 2, 3, 5
1 LIGM - Laboratoire d'Informatique Gaspard-Monge
2 ENPC - École des Ponts ParisTech
3 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
4 Adobe Research
5 Berkeley EECS - Department of Electrical Engineering and Computer Sciences
University of California [Berkeley]
Abstract : This paper presents an end-to-end convolutional neural network (CNN) for 2D-3D exemplar detection. We demonstrate that the ability to adapt the features of natural images to better align with those of CAD rendered views is critical to the success of our technique. We show that the adaptation can be learned by compositing rendered views of textured object models on natural images. Our approach can be naturally incorporated into a CNN detection pipeline and extends the accuracy and speed benefits from recent advances in deep learning to 2D-3D exemplar detection. We applied our method to two tasks: instance detection, where we evaluated on the IKEA dataset [36], and object category detection, where we out-perform Aubry et al. [3] for " chair " detection on a subset of the Pascal VOC dataset.
Type de document :
Communication dans un congrès
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2016, Las Vegas, United States. IEEE, Computer Vision and Pattern Recognition (CVPR), 2016 IEEE Conference on. 〈10.1109/CVPR.2016.648〉
Liste complète des métadonnées

Littérature citée [60 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-01800639
Contributeur : Francisco Massa <>
Soumis le : dimanche 27 mai 2018 - 12:44:53
Dernière modification le : jeudi 26 juillet 2018 - 15:30:25
Document(s) archivé(s) le : mardi 28 août 2018 - 12:28:29

Fichier

Massa_Deep_Exemplar_2D-3D_CVPR...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

UPEC-UPEM | ENPC | PARISTECH | LIGM_A3SI | LIGM | ESIEE-PARIS | IMAGINE

Citation

Francisco Massa, Bryan Russell, Mathieu Aubry. Deep exemplar 2d-3d detection by adapting from real to rendered views. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2016, Las Vegas, United States. IEEE, Computer Vision and Pattern Recognition (CVPR), 2016 IEEE Conference on. 〈10.1109/CVPR.2016.648〉. 〈hal-01800639〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

47

Téléchargements de fichiers

26

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD